在TensorF中重命名已保存模型的变量范围

Question

是否可以在tensorflow中重命名给定模型的变量范围？

例如，我根据教程为MNIST数字创建了一个logistic回归模型：

with tf.variable_scope('my-first-scope'):
    NUM_IMAGE_PIXELS = 784
    NUM_CLASS_BINS = 10
    x = tf.placeholder(tf.float32, shape=[None, NUM_IMAGE_PIXELS])
    y_ = tf.placeholder(tf.float32, shape=[None, NUM_CLASS_BINS])

    W = tf.Variable(tf.zeros([NUM_IMAGE_PIXELS,NUM_CLASS_BINS]))
    b = tf.Variable(tf.zeros([NUM_CLASS_BINS]))

    y = tf.nn.softmax(tf.matmul(x,W) + b)
    cross_entropy = tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(y), reduction_indices=[1]))
    saver = tf.train.Saver([W, b])

... # some training happens

saver.save(sess, 'my-model')

现在我想在'my-first-scope'变量作用域中重新加载保存的模型，然后将所有内容再次保存到一个新文件中，并在新变量作用域'my-second-scope'下保存。

Answer 1

基于keveman的回答，我创建了一个python脚本，您可以执行该脚本来重命名任何TensorFlow检查点的变量：

https://gist.github.com/batzner/7c24802dd9c5e15870b4b56e22135c96

可以替换变量名中的子字符串，并为所有名称添加前缀。用调用脚本

python tensorflow_rename_variables.py --checkpoint_dir=path/to/dir

带可选参数

--replace_from=substr --replace_to=substr --add_prefix=abc --dry_run

以下是脚本的核心功能：

def rename(checkpoint_dir, replace_from, replace_to, add_prefix, dry_run=False):
    checkpoint = tf.train.get_checkpoint_state(checkpoint_dir)
    with tf.Session() as sess:
        for var_name, _ in tf.contrib.framework.list_variables(checkpoint_dir):
            # Load the variable
            var = tf.contrib.framework.load_variable(checkpoint_dir, var_name)

            # Set the new name
            new_name = var_name
            if None not in [replace_from, replace_to]:
                new_name = new_name.replace(replace_from, replace_to)
            if add_prefix:
                new_name = add_prefix + new_name

            if dry_run:
                print('%s would be renamed to %s.' % (var_name, new_name))
            else:
                print('Renaming %s to %s.' % (var_name, new_name))
                # Rename the variable
                var = tf.Variable(var, name=new_name)

        if not dry_run:
            # Save the variables
            saver = tf.train.Saver()
            sess.run(tf.global_variables_initializer())
            saver.save(sess, checkpoint.model_checkpoint_path)

示例：

python tensorflow_rename_variables.py --checkpoint_dir=path/to/dir --replace_from=scope1 --replace_to=scope1/model --add_prefix=abc/

将变量scope1/Variable1重命名为abc/scope1/model/Variable1。